portrait

Tao Du 杜韬

Assistant Professor
Institute for Interdisciplinary Information Sciences (IIIS)
Tsinghua University
Email: taodu.eecs@gmail.com and taodu@tsinghua.edu.cn | Google Scholar | OpenReview

About Me

I am an Assistant Professor at the Institute for Interdisciplinary Information Sciences (IIIS), Tsinghua University. My research combines physics simulation, machine learning, and numerical optimization techniques to solve real-world inverse dynamics problems, e.g., building differentiable simulation platforms for graphics and robotics research, developing computational design pipelines for real-world robots, and understanding simulation-to-reality transfer of dynamic systems.

Before joining Tsinghua, I was a Postdoctoral Associate at MIT CSAIL, advised by Wojciech Matusik and Daniela Rus. I completed my Ph.D. in Computer Science at MIT under the supervision of Wojciech Matusik. I obtained my Master's in Computer Science from Stanford University and my Bachelor's in Computer Software from Tsinghua University.

To prospective students: I am actively looking for students to work on topics in computer graphics, machine learning, and robotics. Students with relevant backgrounds in math, physics, and computer science are all welcome to contact me. Please feel free to drop me an email if you are interested.


Publications

* indicates equal contributions. See my Google Scholar page for an up-to-date list.

ScissorBot: Learning Generalizable Scissor Skill for Paper Cutting via Simulation, Imitation, and Sim2Real

Jiangran Lyu, Yuxing Chen, Tao Du, Feng Zhu, Huiquan Liu, Yizhou Wang, He Wang. CoRL 2024

[Project] [Paper]

QuasiSim: Parameterized Quasi-Physical Simulators for Dexterous Manipulations Transfer

Xueyi Liu, Kangbo Lyu, Jieqiong Zhang, Tao Du, Li Yi. ECCV 2024

[Project] [Paper] [arXiv] [Code] [Slides]

Second-Order Finite Elements for Deformable Surfaces

Qiqin Le, Yitong Deng, Jiamu Bu, Bo Zhu, Tao Du. SIGGRAPH Asia 2023 (Conference track)

[Project] [Paper]

Learning Preconditioners for Conjugate Gradient PDE Solvers

Yichen Li, Peter Yichen Chen, Tao Du, Wojciech Matusik. ICML 2023

[Project] [Paper] [arXiv]

Learning Neural Constitutive Laws from Motion Observations for Generalizable PDE Dynamics

Pingchuan Ma, Peter Yichen Chen, Bolei Deng, Joshua B. Tenenbaum, Tao Du, Chuang Gan, Wojciech Matusik. ICML 2023

[Project] [Paper] [arXiv] [Code]

DexDeform: Dexterous Deformable Object Manipulation with Human Demonstrations and Differentiable Physics

Sizhe Li*, Zhiao Huang*, Tao Chen, Tao Du, Hao Su, Joshua B. Tenenbaum, Chuang Gan. ICLR 2023

[Project] [Paper] [arXiv] [Code]

Sim2Real for Soft Robotic Fish via Differentiable Simulation

John Z. Zhang, Yu Zhang, Pingchuan Ma, Elvis Nava, Tao Du, Philip Arm Wojciech Matusik, Robert K. Katzschmann. IROS 2022

[Paper] [arXiv]

Automatic Co-Design of Aerial Robots Using a Graph Grammar

Allan Zhao, Tao Du, Jie Xu, Josie Hughes, Juan Salazar, Pingchuan Ma, Wei Wang, Daniela Rus, Wojciech Matusik. IROS 2022

[Paper]

Fast Aquatic Swimmer Optimization with Differentiable Projective Dynamics and Neural Network Hydrodynamic Models

Elvis Nava, John Z. Zhang, Mike Yan Michelis, Tao Du, Pingchuan Ma, Benjamin F. Grewe, Wojciech Matusik, Robert K. Katzschmann, ICML 2022

[Paper] [arXiv]

DiffCloth: Differentiable Cloth Simulation with Dry Frictional Contact

Yifei Li, Tao Du, Kui Wu, Jie Xu, Wojciech Matusik. ACM Transactions on Graphics 2022 (SIGGRAPH 2022)

[Project] [arXiv]

RISP: Rendering-Invariant State Predictor with Differentiable Simulation and Rendering for Cross-Domain Parameter Estimation

Pingchuan Ma*, Tao Du*, Joshua B. Tenenbaum, Wojciech Matusik, Chuang Gan. ICLR 2022 (Oral)

[Project] [Paper]

Contact Points Discovery for Soft-Body Manipulations with Differentiable Physics

Sizhe Li*, Zhiao Huang*, Tao Du, Hao Su, Joshua B. Tenenbaum, Chuang Gan. ICLR 2022 (Spotlight)

[Project] [Paper]

Dynamic Visual Reasoning by Learning Differentiable Physics Models from Video and Language

Mingyu Ding, Zhenfang Chen, Tao Du, Ping Luo, Joshua B. Tenenbaum, Chuang Gan. NeurIPS 2021

[Project] [Paper] [Code]

Advanced Soft Robot Modeling in ChainQueen

Andrew Spielberg, Tao Du, Yuanming Hu, Daniela Rus, Wojciech Matusik. Robotica 2021

[Paper]

DiffAqua: A Differentiable Computational Design Pipeline for Soft Underwater Swimmers with Shape Interpolation

Pingchuan Ma, Tao Du, John Z. Zhang, Kui Wu, Andrew Spielberg, Robert K. Katzschmann, Wojciech Matusik. ACM Transactions on Graphics 2021 (SIGGRAPH 2021)

[Project] [Paper] [arXiv] [Code]

PlasticineLab: A Soft-Body Manipulation Benchmark with Differentiable Physics

Zhiao Huang, Yuanming Hu, Tao Du, Siyuan Zhou, Hao Su, Joshua B. Tenenbaum, Chuang Gan. ICLR 2021 (Spotlight)

[Project] [Paper] [Code]

Efficient Continuous Pareto Exploration in Multi-Task Learning

Pingchuan Ma*, Tao Du*, Wojciech Matusik. ICML 2020

[Project] [Paper] [arXiv] [Code] [Talk] [Slides]

Learning-in-the-Loop Optimization: End-to-End Control and Co-Design of Soft Robots through Learned Deep Latent Representations

Andrew Spielberg, Allan Zhao, Yuanming Hu, Tao Du, Daniela Rus, Wojciech Matusik. NeurIPS 2019

[Paper]

Learning to Fly: Computational Controller Design for Hybrid UAVs with Reinforcement Learning

Jie Xu, Tao Du, Michael Foshey, Beichen Li, Bo Zhu, Adriana Schulz, Wojciech Matusik. ACM Transactions on Graphics 2019 (SIGGRAPH 2019)

[Project] [Paper] [Code]

Convolutional Wasserstein Distances: Efficient Optimal Transportation on Geometric Domains

Justin Solomon, Fernando de Goes, Gabriel Peyré, Marco Cuturi, Adrian Butscher, Andy Nguyen, Tao Du, Leonidas Guibas. ACM Transactions on Graphics 2015 (SIGGRAPH 2015)

[Paper] [Code]


Thesis

Differentiable Simulation Methods for Robotic Agent Design

Ph.D. thesis

[Thesis] [Video]


Service

Program Committee: SIGGRAPH, SIGGRAPH Asia
Journal paper reviewer: TOG, TVCG, IJRR, T-RO, RA-L
Conference paper reviewer: SIGGRAPH, SIGGRAPH Asia, NeurIPS (Outstanding Reviewer), ICML (Outstanding Reviewer), ICLR, RSS